Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    of from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bluetooth
    -0.06
    eren
    -0.06
     아무
    -0.06
    capability
    -0.06
     stylish
    -0.06
    ざ
    -0.06
     여성
    -0.06
     consul
    -0.06
    choose
    -0.06
    .Insert
    -0.06
    POSITIVE LOGITS
    elage
    0.07
     comprises
    0.07
     ranking
    0.07
    predicted
    0.06
    ции
    0.06
    AL
    0.06
     LoginPage
    0.06
    �
    0.06
     handwritten
    0.06
    HING
    0.06
    Act Density 0.027%

    No Known Activations